synth-llava / README.md
TieuDaoChanNhan's picture
Fix dataset_info.features: add missing task column (schema/metadata mismatch, data itself was already correct)
53f6ad6 verified
|
Raw
History Blame Contribute Delete
2.65 kB
metadata
license: other
dataset_info:
  features:
    - name: id
      dtype: string
    - name: task
      dtype: string
    - name: text
      dtype: string
  splits:
    - name: train
      num_bytes: 1223425889
      num_examples: 1207998
  download_size: 294631286
  dataset_size: 1223425889
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*

synth-llava

Reverse-direction augment (v5) of the synth_llava / synth_llava2 (image+caption) training text -- 1,207,998 rows (603,999 source rows x 2 tasks). Replaces this repo's prior single-task release (v4, instruction-phrasing-pool augment) -- the old content isn't used by anything going forward. <seed2_N> payload tokens for the forward task are byte-identical to the prior release; the reverse task is new.

Why this exists

Every prior release only trained image->caption (forward). Huu's own Discord stance (2026-08-03), in response to a "isn't caption->seed2 counter-intuitive?" question: "seed2 is bidirectional" -- the tokenizer's own design intent already includes text->image conditioning (its reconstruction path is a diffusion model, SD2.1-unclip, conditioned on the seed2 sequence), not just image understanding. Considered and initially set aside earlier in the same investigation for lacking a cheap, verifiable round-trip (unlike cosmos/avclm/SNAC/agent, which have real decoders) -- but that's a property of evaluation, not a reason to skip training on it (the same logic applies to any text-to-image diffusion model).

What changed

Tokens are unchanged -- reuses the already-encoded <seed2_N> sequence from the prior release with no re-tokenization. Adds one new task per source row:

  • forward (unchanged, byte-identical to v4): <seed2>...</seed2> + one of 7 instruction phrasings -> <caption>...</caption>
  • reverse (NEW): one of 7 "draw/imagine/visualize" instruction phrasings + <caption>...</caption> -> <seed2>...</seed2>. Instruction variant assigned deterministically per row (sha256(id + "_reverse") % 7).

Format

[forward]
USER: <seed2> <seed2_N> ... </seed2> <one of 7 instruction phrasings> ASSISTANT:
<think>
</think>
<caption> ... </caption>

[reverse]
USER: <one of 7 draw/imagine phrasings> <caption> ... </caption> ASSISTANT:
<think>
</think>
<seed2> <seed2_N> ... </seed2>

Base

Synthetic image+caption pairs from mixture-vitae-backup/MixtureVitae-Backup, tokenized with the Seed2 semantic image tokenizer (<seed2_N>, vocab 8192) -- the only tokenizer in this project that accepts a standalone image with no video/action context.